© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 235921
    Prev
    Next
    INDEX
    Explanations

    bullet points and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    era
    0.42
    aların
    0.42
    ey
    0.41
    ைகளின்
    0.40
     Histoire
    0.38
    aven
    0.36
     artistique
    0.35
    '
    0.35
     cend
    0.35
    自身的
    0.35
    POSITIVE LOGITS
    節
    0.43
     можете
    0.43
    นะนำ
    0.42
     nabíz
    0.42
    ប្រើ
    0.40
     thymus
    0.40
     нама
    0.40
     infecting
    0.39
    ៀប
    0.39
     تريد
    0.39
    Activations Density 0.001%

    No Known Activations